Text Generation
Transformers
Safetensors
qwen2
unsloth
grpo
sft
fortran
reinforcement learning
conversational
text-generation-inference
Instructions to use GiuLeo01/FortranCodeGen-3B-SynthData with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GiuLeo01/FortranCodeGen-3B-SynthData with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="GiuLeo01/FortranCodeGen-3B-SynthData") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("GiuLeo01/FortranCodeGen-3B-SynthData") model = AutoModelForCausalLM.from_pretrained("GiuLeo01/FortranCodeGen-3B-SynthData", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use GiuLeo01/FortranCodeGen-3B-SynthData with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "GiuLeo01/FortranCodeGen-3B-SynthData" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GiuLeo01/FortranCodeGen-3B-SynthData", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/GiuLeo01/FortranCodeGen-3B-SynthData
- SGLang
How to use GiuLeo01/FortranCodeGen-3B-SynthData with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "GiuLeo01/FortranCodeGen-3B-SynthData" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GiuLeo01/FortranCodeGen-3B-SynthData", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "GiuLeo01/FortranCodeGen-3B-SynthData" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GiuLeo01/FortranCodeGen-3B-SynthData", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Desktop
- Docker Model Runner
How to use GiuLeo01/FortranCodeGen-3B-SynthData with Docker Model Runner:
docker model run hf.co/GiuLeo01/FortranCodeGen-3B-SynthData
Update README.md
Browse files
README.md
CHANGED
|
@@ -3,9 +3,9 @@ library_name: transformers
|
|
| 3 |
tags:
|
| 4 |
- unsloth
|
| 5 |
- grpo
|
| 6 |
-
- reinforcement_learning
|
| 7 |
- sft
|
| 8 |
- fortran
|
|
|
|
| 9 |
base_model:
|
| 10 |
- Qwen/Qwen2.5-Coder-3B-Instruct
|
| 11 |
---
|
|
@@ -54,7 +54,6 @@ output = generator([{"role": "user", "content": question}], max_new_tokens=128,
|
|
| 54 |
print(output["generated_text"])
|
| 55 |
```
|
| 56 |
|
| 57 |
-
[More Information Needed]
|
| 58 |
|
| 59 |
## Training Details
|
| 60 |
|
|
@@ -62,6 +61,19 @@ print(output["generated_text"])
|
|
| 62 |
|
| 63 |
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 64 |
|
| 65 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
|
| 67 |
-
### Training Procedure
|
|
|
|
| 3 |
tags:
|
| 4 |
- unsloth
|
| 5 |
- grpo
|
|
|
|
| 6 |
- sft
|
| 7 |
- fortran
|
| 8 |
+
- rl
|
| 9 |
base_model:
|
| 10 |
- Qwen/Qwen2.5-Coder-3B-Instruct
|
| 11 |
---
|
|
|
|
| 54 |
print(output["generated_text"])
|
| 55 |
```
|
| 56 |
|
|
|
|
| 57 |
|
| 58 |
## Training Details
|
| 59 |
|
|
|
|
| 61 |
|
| 62 |
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 63 |
|
| 64 |
+
The goal of this experiment was to specialize a model in a complex task, like Fortran code generation, without using manually annotated data, which is particularly hard to find for this programming language.
|
| 65 |
+
|
| 66 |
+
#### Supervised Data
|
| 67 |
+
1) A subset of the MBPP dataset (~600 examples) was selected.
|
| 68 |
+
2) The task descriptions were automatically adapted to Fortran using precise instructions, using OpenAI o3-mini.
|
| 69 |
+
3) Tasks were filtered using embeddings and manually reviewed to ensure that no examples too similar to HumanEval tasks were included in the training set.
|
| 70 |
+
4) Each task was automatically labeled using three stronger (and bigger) models: OpenAI o3-mini, Qwen 2.5 Coder 32B, and OpenAI GPT-4o.
|
| 71 |
+
5) Labels were automatically validated through unit tests.
|
| 72 |
+
6) Only correct solutions were kept, at most one per task, prioritized in the following order: OpenAI o3-mini > Qwen 2.5 Coder 32B > OpenAI GPT-4o.
|
| 73 |
+
|
| 74 |
+
This simple process led to the creation of a small, synthetically labeled training set used for supervised fine-tuning.
|
| 75 |
+
|
| 76 |
+
IMPORTANT: Do not validate this model on MBPP-derived benchmarks due to the data overlap.
|
| 77 |
+
|
| 78 |
+
### Training Procedure
|
| 79 |
|
|
|